目标检测:CoCo类型的json文件转换成Voc类型的xml文件（一张图片一个xml）并进行可视化检验

代码可以直接使用，只需要修改相应路径即可，同时根据json的不同做一些相应改进

#translate coco_json to xml
#使用时仅需修改22、24、25行路径文件
import os
import time
import json
import shutil
import pandas as pd
from tqdm import tqdm
from pycocotools.coco import COCO

def trans_id(category_id):
    names = []
    namesid = []
    for i in range(0, len(cats)):
        names.append(cats[i]['name'])
        namesid.append(cats[i]['id'])
        #print('id:{1}\t {0}'.format(names[i], namesid[i]))
    index = namesid.index(category_id)
    return index


root = '/home/admin1/data/fsod/'  # 你图片数据集所在目录
dataType = 'images'
anno  = '/home/admin1/data/fsod/annotations/fsod_train.json' # 你json文件所在目录
xml_dir = '/home/admin1/data/fsod/testxml' # 你存放xml所在目录

coco = COCO(anno)  # 读文件
cats = coco.loadCats(coco.getCatIds())  # 这里loadCats就是coco提供的接口，获取类别

# Create anno dir
dttm = time.strftime("%Y%m%d%H%M%S", time.localtime())
if os.path.exists(xml_dir):
    os.rename(xml_dir, xml_dir + dttm)
os.mkdir(xml_dir)


with open(anno, 'r') as load_f:
    f = json.load(load_f)

imgs = f['images']

df_cate = pd.DataFrame(f['categories'])
df_cate_sort = df_cate.sort_values(["id"], ascending=True)
categories = list(df_cate_sort['name'])



# # 打开文件并写入列表中的元素
# with open('LVISname.txt', 'w') as f:
#     for item in categories:
#         # 去除标点符号并转换为小写
#         clean_item = ''.join([c for c in item if c not in punctuation]).lower()
#         # 写入文件
#         f.write(clean_item + '\n')
print('categories = ',categories)
df_anno = pd.DataFrame(f['annotations'])


for i in tqdm(range(len(imgs))):
    xml_content = []
    file_name = imgs[i]['file_name']
    last_part = file_name.split("/")[-1]  #原始的file_name带有路径,这里是去掉路径只需要文件名
    last_part=last_part[:-4]
    height = imgs[i]['height']
    img_id = imgs[i]['id']
    width = imgs[i]['width']

    xml_content.append("<annotation>")
    xml_content.append("	<folder>VOC2007</folder>")
    xml_content.append("	<filename>" + str(last_part)+'.jpg' + "</filename>")
    xml_content.append("	<size>")
    xml_content.append("		<width>" + str(width) + "</width>")
    xml_content.append("		<height>" + str(height) + "</height>")
    xml_content.append("	</size>")
    xml_content.append("	<segmented>0</segmented>")
    # 通过img_id找到annotations
    annos = df_anno[df_anno["image_id"].isin([img_id])]

    for index, row in annos.iterrows():
        bbox = row["bbox"]
        category_id = row["category_id"]
        cate_name = categories[trans_id(category_id)]
        cate_name = cate_name.replace('&','').replace(' ', '-')
        # add new object
        xml_content.append("	<object>")
        xml_content.append("		<name>" + cate_name + "</name>")
        xml_content.append("		<pose>Unspecified</pose>")
        xml_content.append("		<truncated>0</truncated>")
        xml_content.append("		<difficult>0</difficult>")
        xml_content.append("		<bndbox>")
        xml_content.append("			<xmin>" + str(int(bbox[0])) + "</xmin>")
        xml_content.append("			<ymin>" + str(int(bbox[1])) + "</ymin>")
        xml_content.append("			<xmax>" + str(int(bbox[0] + bbox[2])) + "</xmax>")
        xml_content.append("			<ymax>" + str(int(bbox[1] + bbox[3])) + "</ymax>")
        xml_content.append("		</bndbox>")
        xml_content.append("	</object>")
    xml_content.append("</annotation>")

    x = xml_content
    xml_content = [x[i] for i in range(0, len(x)) if x[i] != "\n"]
    ### list存入文件
    xml_path = os.path.join(xml_dir, str(last_part) + '.xml')
    with open(xml_path, 'w+', encoding="utf8") as f:
        f.write('\n'.join(xml_content))
    xml_content[:] = []

 转换完成以后,可以根据图片和xml文件画出框,检验自己转换得是否正确,代码如下:

import cv2
import os
import xml.etree.ElementTree as ET

# 原始图片和标注文件夹路径 这里是放在一个路径下,你可以分开放重新简单修改一下即可
input_folder = '/home/admin1/data/fsod/test'

output_folder = '/home/admin1/data/fsod/drawtest'

# 确保输出文件夹存在
if not os.path.exists(output_folder):
    os.makedirs(output_folder)

# 遍历文件夹中的所有文件
for filename in os.listdir(input_folder):
    # 检查文件是否为jpg和xml
    if filename.endswith('.jpg') and os.path.isfile(os.path.join(input_folder, filename[:-4] + '.xml')):
        # 读取jpg和xml文件
        img = cv2.imread(os.path.join(input_folder, filename))
        xml_file = os.path.join(input_folder, filename[:-4] + '.xml')
        try:
            tree = ET.parse(xml_file)
            root = tree.getroot()
        except:
            print(xml_file)

        # 遍历xml中的所有标注
        for obj in root.iter('object'):
            difficult = obj.find('difficult').text
            bbox = obj.find('bndbox')
            xmin = int(bbox.find('xmin').text)
            ymin = int(bbox.find('ymin').text)
            xmax = int(bbox.find('xmax').text)
            ymax = int(bbox.find('ymax').text)
            label = obj.find('name').text
            # 只处理非困难的标注
            if difficult == '0':
                # 在图片上绘制矩形框并保存图片
                cv2.rectangle(img, (xmin, ymin), (xmax, ymax), (0, 255, 0), 2)  # 绘制绿色矩形框，你可以根据需要调整颜色和线宽
                cv2.putText(img, label, (xmin, ymin-10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,255,0), 2)  # 在矩形框上方写入类别标签，你可以根据需要调整颜色、字体和大小等参数
                cv2.imwrite(os.path.join(output_folder, filename), img)  # 保存新的图片到输出文件夹，文件名保持不变